lmstudio-ai / lmstudio-ai/mlx-engine
[Feature]: turboquant: KV cache
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 133
- Avg merge
- 21h 6m
- Merged PRs (30d)
- 1
Description
I'd like to benefit from KV Cache quantization on macOS
https://github.com/OnlyTerp/turboquant
https://github.com/mitkox/vllm-turboquant
https://github.com/scrya-com/rotorquant
https://github.com/VectorDB-NTU/RaBitQ-Library
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the linked turboquant, vllm-turboquant, rotorquant, and RaBitQ-Library projects to understand KV-cache quantization approaches relevant to macOS. Then inspect mlx-engine's existing cache implementation and determine the supported quantization behavior, validation criteria, and tests needed for this feature.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- macos, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100